[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VX68P9RZ58VB63FH2VV5C":3,"skill-same:01M78VX68P9RZ58VB63FH2VV5C":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78VX68P9RZ58VB63FH2VV5C","retrieval-qa",null,"Use DeepPavlov retrieval, ranking, FAQ, SQuAD, ODQA, and KBQA workflows with correct config, data, index, and input\u002Foutput choices.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retrieval-qa\ndescription: \"Use DeepPavlov retrieval, ranking, FAQ, SQuAD, ODQA, and KBQA\n  workflows with correct config, data, index, and input\u002Foutput choices.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# retrieval-qa\n\nUse this sub-skill when a DeepPavlov task involves questions, contexts, documents, document IDs, ranking scores, FAQ categories, answer spans, ODQA pipelines, or Wikidata-style KBQA queries.\n\n## Route quickly\n\n- Generic DeepPavlov config syntax, nested `config_path`, `overwrite`, registry, train\u002Fevaluate\u002Fpredict modes, and component wiring: [..\u002Fpipelines\u002FSKILL.md](..\u002Fpipelines\u002FSKILL.md).\n- Generic text classification, NER, entity extraction, spelling, syntax, morphology, embedders, or relation extraction outside retrieval\u002FQA: [..\u002Ftext-models\u002FSKILL.md](..\u002Ftext-models\u002FSKILL.md).\n- REST or socket deployment after a retrieval\u002FQA config runs locally: [..\u002Fserving\u002FSKILL.md](..\u002Fserving\u002FSKILL.md).\n- Shared install\u002Fimport\u002Fcache\u002Fbackend problems: [..\u002F..\u002Freferences\u002Ftroubleshooting.md](..\u002F..\u002Freferences\u002Ftroubleshooting.md).\n\n## Start here\n\n1. Choose the workflow family in [references\u002Fmodel-catalog.md](references\u002Fmodel-catalog.md): `doc_retrieval`, `ranking`, `squad`, `odqa`, `kbqa`, or `faq`.\n2. Prepare the required local data\u002Findex layout with [references\u002Fdata-and-indexing.md](references\u002Fdata-and-indexing.md).\n3. For a safe local document-retrieval template, generate a two-document config with [scripts\u002Ftiny_retrieval_config.py](scripts\u002Ftiny_retrieval_config.py).\n4. Diagnose retrieval\u002FQA-specific failures with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) before escalating to root troubleshooting.\n\n## Decision hints\n\n- Use `squad` when every question has an explicit context batch.\n- Use `odqa` when the user supplies only questions and expects retrieval plus answer extraction over a document collection.\n- Use `doc_retrieval` when the deliverable is document IDs\u002Ftitles\u002Fscores rather than answer spans.\n- Use `ranking` for response ranking or KBQA relation\u002Fpath ranking; route ordinary classifiers to `text-models`.\n- Use `kbqa` for Wikidata-style entity\u002Frelation\u002Fquery generation outputs.\n- Use `faq` for fastText\u002Flogistic-regression FAQ intent\u002Fcategory lookup or simple CSV FAQ corpora.\n\nDo not reopen the original repository checkout for runtime guidance; use the bundled references and scripts in this sub-skill tree.\n","# retrieval-qa\n\nUse this sub-skill when a DeepPavlov task involves questions, contexts, documents, document IDs, ranking scores, FAQ categories, answer spans, ODQA pipelines, or Wikidata-style KBQA queries.\n\n## Route quickly\n\n- Generic DeepPavlov config syntax, nested `config_path`, `overwrite`, registry, train\u002Fevaluate\u002Fpredict modes, and component wiring: [..\u002Fpipelines\u002FSKILL.md](..\u002Fpipelines\u002FSKILL.md).\n- Generic text classification, NER, entity extraction, spelling, syntax, morphology, embedders, or relation extraction outside retrieval\u002FQA: [..\u002Ftext-models\u002FSKILL.md](..\u002Ftext-models\u002FSKILL.md).\n- REST or socket deployment after a retrieval\u002FQA config runs locally: [..\u002Fserving\u002FSKILL.md](..\u002Fserving\u002FSKILL.md).\n- Shared install\u002Fimport\u002Fcache\u002Fbackend problems: [..\u002F..\u002Freferences\u002Ftroubleshooting.md](..\u002F..\u002Freferences\u002Ftroubleshooting.md).\n\n## Start here\n\n1. Choose the workflow family in [references\u002Fmodel-catalog.md](references\u002Fmodel-catalog.md): `doc_retrieval`, `ranking`, `squad`, `odqa`, `kbqa`, or `faq`.\n2. Prepare the required local data\u002Findex layout with [references\u002Fdata-and-indexing.md](references\u002Fdata-and-indexing.md).\n3. For a safe local document-retrieval template, generate a two-document config with [scripts\u002Ftiny_retrieval_config.py](scripts\u002Ftiny_retrieval_config.py).\n4. Diagnose retrieval\u002FQA-specific failures with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) before escalating to root troubleshooting.\n\n## Decision hints\n\n- Use `squad` when every question has an explicit context batch.\n- Use `odqa` when the user supplies only questions and expects retrieval plus answer extraction over a document collection.\n- Use `doc_retrieval` when the deliverable is document IDs\u002Ftitles\u002Fscores rather than answer spans.\n- Use `ranking` for response ranking or KBQA relation\u002Fpath ranking; route ordinary classifiers to `text-models`.\n- Use `kbqa` for Wikidata-style entity\u002Frelation\u002Fquery generation outputs.\n- Use `faq` for fastText\u002Flogistic-regression FAQ intent\u002Fcategory lookup or simple CSV FAQ corpora.\n\nDo not reopen the original repository checkout for runtime guidance; use the bundled references and scripts in this sub-skill tree.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-qa",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-qa",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-qa","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdata-and-indexing.md","REFERENCE","参考文档",9295,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa\u002Freferences\u002Fdata-and-indexing.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmodel-catalog.md",7163,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa\u002Freferences\u002Fmodel-catalog.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7004,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Ftiny_retrieval_config.py","SCRIPT","脚本",6129,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeeppavlov\u002Fsub-skills\u002Fretrieval-qa\u002Fscripts\u002Ftiny_retrieval_config.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]